CN114092168A

CN114092168A - Service processing method, device, storage medium and electronic equipment

Info

Publication number: CN114092168A
Application number: CN202010875939.8A
Authority: CN
Inventors: 高明辉; 马超逸; 高久翀
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2020-08-25
Filing date: 2020-08-25
Publication date: 2022-02-25

Abstract

The specification discloses a business processing method, a business processing device, a storage medium and an electronic device, wherein a model is trained according to a sample order with a known historical execution mode, so that the model can learn the capability of judging the execution mode of the order through first data. And then, determining the execution mode of the pending order with an unknown historical execution mode by adopting the trained model. It can be seen that the present specification is at least capable of supplementing the pending order with missing data characterizing the execution mode. Further, after obtaining the execution manner of each historical order, the business corresponding to each order in the area may be processed in units of areas according to the execution manner of the historical orders in the area. It can be seen that the processes in this specification can at least compare the execution patterns of orders in an area, and/or can use the execution pattern of historical orders in the area as a priori of other orders in the area, so that each order can be properly processed.

Description

Service processing method, device, storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of internet technologies, and in particular, to a method and an apparatus for processing a service, a storage medium, and an electronic device.

Background

With the acceleration of urban life rhythm, the service mode of 'internet + logistics' is rapidly developed. At present, the logistics service mode realized by distribution capacity plays an irreplaceable role in production and life.

When a service corresponding to an order is processed, it is usually necessary to compare the situation of the order with situations of other orders except the order, so that it is possible to know that the execution situation of the order is accurately evaluated. However, in an actual scenario, due to influences of environments, human beings, and the like, data of the other orders cannot be comprehensively acquired. The data available for reference when processing the service corresponding to the order is limited, which increases the difficulty of processing the service process corresponding to the order.

Therefore, how to properly process the business corresponding to the order according to the limited data becomes a problem to be solved urgently.

Disclosure of Invention

Embodiments of the present specification provide a method, an apparatus, a storage medium, and an electronic device for service processing, so as to partially solve the above problems in the prior art.

The embodiment of the specification adopts the following technical scheme:

a method of traffic processing, the method comprising:

determining a sample order with a known execution mode and a pending order with an unknown execution mode in each historical order;

determining a training sample according to the acquired first data of each sample order; determining a label according to the execution mode of the sample order;

training a preset model according to the determined training samples and labels to obtain a trained model;

aiming at each undetermined order, determining an execution mode adopted when the undetermined order is executed by adopting the trained model according to the first data of the undetermined order;

for each preset area, determining a historical order executed in the area in each historical order;

processing the business corresponding to the order in the area according to the execution mode of each historical order executed in the area, wherein the order in the area comprises: at least one of historical orders in the area, incomplete orders in the area.

Optionally, in each historical order, determining a sample order with a known execution mode and a pending order with an unknown execution mode specifically includes:

for each historical order, obtaining data generated when the historical order is executed historically, wherein the data comprises: at least one of the first data and the second data;

and judging whether the data of the historical order comprises second data, if so, determining that the historical order is a sample order, and if not, determining that the historical order is an undetermined order.

Optionally, determining a training sample according to the obtained first data of the sample order, specifically including:

determining a first specified range around the task point according to a preset first distance aiming at the task point of the sample order;

for each time when the sample order is executed within the first specified range, determining first data corresponding to the time in the data of the sample order;

and determining a training sample according to the first data corresponding to each moment and the time sequence of each first data.

Optionally, the first data comprises: data of a wireless communication signal;

determining a training sample according to the first data corresponding to each moment and the time sequence of each first data, specifically comprising:

determining at least one of the number of the wireless communication signals acquired at the moment, the comprehensive signal strength of each wireless communication signal and the signal strength of each target wireless communication signal according to the data of the wireless communication signal corresponding to the moment, and taking the data as available data corresponding to the moment; wherein the target wireless communication signal is: in a sequence formed by the collected signal intensity of each wireless communication signal from large to small, the signal intensity of the wireless communication signal is positioned before a preset sequence;

determining the characteristics corresponding to the moment according to the available data corresponding to the moment;

and determining a training sample according to the corresponding characteristics of each moment and the time sequence of each first data.

Optionally, determining the label according to the execution mode of the sample order specifically includes:

determining a second specified range around the task point according to a preset second distance aiming at the task point of the sample order;

determining an execution mode adopted when the sample order is executed according to second data generated when the sample order is executed in the second specified range;

and determining the label of the sample order according to the execution mode of the sample order.

Optionally, the second data comprises: atmospheric pressure data of the environment; the execution mode comprises the following steps: at least one of an elevator execution mode and a walking execution mode;

determining an execution mode adopted when the sample order is executed according to second data generated when the sample order is executed in the second specified range, specifically comprising:

determining a change in atmospheric pressure data of an environment at which the sample order was executed within a second specified range of the task point;

if the change meets the preset condition, determining that the execution mode when the sample order is executed is the execution mode of an elevator; and if not, determining that the execution mode when executing the sample order is the execution mode of walking.

Optionally, processing the service corresponding to the order in the area according to the execution manner of each historical order executed in the area specifically includes:

determining an execution mode corresponding to the area according to the execution mode of each historical order executed in the area;

for each order, determining the area where the order is located in each area as a target area of the order;

and processing the service corresponding to the order according to the execution mode corresponding to the target area.

The service processing apparatus provided in this specification includes:

the order determining module is configured to determine a sample order with a known execution mode and a pending order with an unknown execution mode in each historical order;

the training sample and label determining module is configured to determine a training sample according to the acquired first data of each sample order; determining a label according to the execution mode of the sample order;

the training module is configured to train a preset model according to the determined training samples and labels to obtain a trained model;

the execution mode determining module is configured to determine, for each pending order, an execution mode to be adopted when the pending order is executed by adopting the trained model according to the first data of the pending order;

the historical order determining module is configured to determine, for each preset area, a historical order executed in the area in each historical order;

a service processing module, configured to process a service corresponding to each historical order executed in the area according to an execution manner of each historical order executed in the area, where the order in the area includes: at least one of historical orders in the area, incomplete orders in the area.

The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the service processing method described above.

The electronic device provided by the present specification includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the service processing method when executing the program.

The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects:

the business processing method, the business processing device, the storage medium and the electronic device in the embodiments of the present specification train the model according to the sample order with a historically known execution mode, so that the model can learn the capability of judging the execution mode of the order by using the first data. And then, determining the execution mode of the pending order with an unknown historical execution mode by adopting the trained model. It can be seen that the present specification is at least capable of supplementing the pending order with missing data characterizing the execution mode. Further, after obtaining the execution manner of each historical order, the business corresponding to each order in the area may be processed in units of areas according to the execution manner of the historical orders in the area. It can be seen that the processes in this specification can at least compare the execution patterns of orders in an area, and/or can use the execution pattern of historical orders in the area as a priori of other orders in the area, so that each order can be properly processed.

Drawings

The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:

fig. 1 is a process of service processing provided by an embodiment of the present specification;

fig. 2a is a schematic view of the air pressure change when the elevator is going upstairs and downstairs;

FIG. 2b is a schematic view showing the change of air pressure when the operation is not going upstairs or downstairs;

FIG. 3 is a process for determining an order execution mode by a model provided in an embodiment of the present description;

fig. 4 is a schematic structural diagram of a service processing apparatus provided in an embodiment of the present specification;

fig. 5 is a schematic diagram of an electronic device corresponding to fig. 1 provided in an embodiment of the present disclosure.

Detailed Description

In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the specification without making any creative effort belong to the protection scope of the specification.

In a practical scenario, each data generated during the order execution process (the data includes, but is not limited to, data related to the execution environment of the order) is collected by the terminal that delivers the capacity. This makes the type of data collected, the amount of data collected, somewhat affected by the terminal that delivers the capacity.

In addition, there are other factors that affect the acquired data, such as data loss caused by poor data transmission quality, which is not exemplified here.

The data acquisition capability of the terminal is mostly determined by the performance of the terminal itself. If a terminal does not have the function of collecting certain data, the type of data will be lost when the terminal is adopted to execute orders. For example, if a terminal does not have a positioning function, it is impossible to position the delivery capacity of the terminal when an order is executed. The missing and distortion of the order data will affect the guiding ability of the data generated during the historical order execution to the subsequently executed order to a certain extent.

The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.

Fig. 1 is a service processing process provided in this specification, which may specifically include one or more of the following steps:

s100: in each historical order, a sample order with a known execution mode and a pending order with an unknown execution mode are determined.

The order referred to in this specification may be an order executed by delivery capacity, such as a take-away order, a courier order, and the like. The historical orders may be orders that were executed at the historical time, have currently been completed, and/or are being executed at both the historical time and the current time.

In this specification, the subject who performs the "execute" operation on the order may be various. For example, the executing agent may be at least one of a user corresponding to the order (for example, the user corresponding to the order may be a user performing an order placing operation for the order), a server involved in an order executing process (optionally, the process of business processing in this specification is executed by the server), a merchant corresponding to the order (for example, a merchant generating goods corresponding to the order), and a distribution capacity for executing the order.

Where the executing agent is a delivery capacity that executes the order, the manner of execution may be the action taken by the delivery capacity in executing the order. For example, the execution mode can be an elevator execution mode or a walking execution mode; the execution mode can also be that the distribution capacity is sent by telephone/short message notification to the user corresponding to the order, or the distribution capacity is directly knocked after reaching the task point.

Further, in scenarios where orders are filled by shipping capacity, there may also be instances where the orders are filled by merchants and/or users. For example, after the user goes downstairs, the process of obtaining the goods corresponding to the order from the delivery capacity is to execute the order by the user, and at this time, the execution mode of the order is the mode executed by the user.

The present specification classifies each historical order according to whether the execution mode is known. If the execution mode of a historical order is known, the historical order is a sample order; if not, the historical order is a pending order.

In addition, the specification does not limit the type, specific setting position, and operation manner of the terminal. The terminal may be a handheld terminal for the delivery capacity or a terminal installed on a carrier used when the delivery capacity executes an order.

Alternatively, the service processing procedure in this specification may be executed by a server.

S102: determining a training sample according to the acquired first data of each sample order; and, the label is determined according to the execution mode of the sample order.

As can be seen from the foregoing, the first data in the present specification may be data acquired (acquired may be in a collected manner) during execution of the sample order. The first data may characterize how the sample order is executed from at least one of the following dimensions: taking an environment (e.g., a traffic environment, a geographic environment, etc.) corresponding to the manner of execution by which the sample order was executed, the actions taken when the delivery capacity executed the order, and the resources available when executing the sample order.

The method for learning the execution mode of the history order is not particularly limited in this specification. Alternatively, the execution mode of the history order may be known from data generated when the history order is executed.

For example, when the execution subject is delivery capacity for executing the order, the delivery capacity may determine the execution mode of the historical order, and an item corresponding to the determination may be selected (by the terminal) from preset execution mode options. In addition, the execution mode of the historical order can be obtained from the data automatically collected by the terminal.

The present specification does not specifically limit the division criteria for the different execution modes.

At least part of data collected in the order execution process may have a certain degree of relevance, and the relevance is not obvious, and a large amount of data can be obtained by mining and analyzing in a proper mode. The process in the specification can establish an association relationship between the first data and the execution mode through a large number of sample orders, so as to realize the representation of the execution mode through the first data.

Alternatively, the execution mode of the sample order may be directly used as the label when determining the label.

The specification does not limit the execution sequence of the training sample determination and the label determination.

S104: and training a preset model according to the determined training samples and labels to obtain a trained model.

The preset model in the present specification may be a neural network having a classification and/or regression function.

The training process for the preset model may be supervised training. Specifically, the training process may be: and inputting the training sample obtained according to the sample order into the preset model aiming at each sample order to obtain an output intermediate result. A difference between the intermediate result and the label obtained from the sample order is determined. And adjusting at least part of parameters (such as weight values) of the preset model by taking the minimization of the difference as a training target to obtain the trained model.

S106: and aiming at each undetermined order, determining an execution mode adopted when the undetermined order is executed by adopting the trained model according to the first data of the undetermined order.

As can be seen from the foregoing, the execution mode of the pending order cannot be obtained by the existing method. It will be appreciated that there is a degree of variability between orders and that data generated during execution of different orders can convey different information. In order to more comprehensively and accurately process the information transmitted in each order, the data of each order is required to have a certain degree of integrity. However, the data of the pending order representing the execution mode is missing, so that the information of the execution mode of the pending order cannot be effectively processed.

One of the objectives to be achieved by the process of the present specification is to determine an execution mode of an undetermined order to make up for the defect of data loss of the undetermined order.

If the trained model in which the association relationship between the first data and the execution mode is learned is obtained in the foregoing step, the execution mode of the pending order can be obtained by using the trained model on the basis of obtaining the first data of the pending order.

Optionally, the process of determining the execution mode of the pending order may be: and inputting the first data of the pending order into the trained model aiming at each pending order to obtain the execution mode of the pending order output by the trained model.

Thus, first data and execution modes of each historical order (including the sample order and the pending order) are obtained.

S108: for each preset area, determining the historical orders executed in the area in the historical orders.

The area referred to in this specification may be an area divided according to a geographical location. For example, a residential area may be regarded as an area, and a business area may be regarded as an area. The granularity adopted when dividing the regions can be determined according to the actual scene and/or the business target. For example, one residential area may be regarded as one area; further division can be performed for a residential area, and each unit of the residential area is taken as an area.

In an alternative embodiment of the present specification, it may be determined whether the order is in the area according to a positional relationship between the task point and the area of the order. Specifically, if the task point of the order is located in the area, the area may be used as the area where the order is located.

The specification does not limit the specific meaning of the task point, and the task point may be a point or a range. Specifically, the task point may be at least one of a pick point (e.g., a geographic location of a merchant accepting the order), a delivery point (e.g., a geographic location of a user corresponding to the order being sent).

S110: processing the business corresponding to the order in the area according to the execution mode of each historical order executed in the area, wherein the order in the area comprises: historical orders in the area, orders in the area.

A service in this specification may be a pending transaction. The transaction may be a pending transaction for an execution process of the order; or may be a pending transaction for the order after execution of the order is complete.

The specific meaning of "order execution complete" can be determined according to the actual requirement. Specifically, when the execution subject is a user corresponding to the order, a time when the user sends the order to the server may be determined as a time when the order execution is completed. When the execution agent is the delivery capacity for executing the order, the time when the delivery capacity delivers the product corresponding to the order to the user corresponding to the order may be the time when the execution of the order is completed. An order that does not reach the execution completion time in the order execution process may be an unfinished order in this specification.

The specific meaning of the service corresponding to the order can also be determined according to the actual requirement.

Specifically, when the order is a history order, the service corresponding to the order may be: the order is at least one of identified (the identification can be used for determining the business processing mode of the unfinished order), and the effect of the execution mode of the order executed by the execution main body is measured (optionally, the effect can be represented by efficiency).

For example, when the executing entity is the delivery capacity for executing the order, the business corresponding to the order may include: the capacity information of the delivery capacity is managed. The information about the delivery capacity may be managed based on the efficiency of the delivery capacity to execute the order in the execution manner and whether it is appropriate to measure the delivery capacity to execute the order in the execution manner.

Further, when the order is an incomplete order, the service corresponding to the order may be: planning a path taken by a delivery capacity to execute the incomplete order for the incomplete order, and determining a difficulty of execution of the incomplete order (optionally, the difficulty of execution may be used to determine resources that will be consumed to execute the order).

When the business process in this specification is used to plan a path taken by the delivery capacity to execute the incomplete order for the incomplete order, the meaning of the path may be determined according to a specific scenario. In particular, the path may be the various locations that the delivery capacity executing the incomplete order is expected to reach when executing the incomplete order, where a location may represent a geographic location (e.g., latitude and longitude coordinates). Optionally, the locations may have a sequential relationship of successive arrivals, which may be characterized by the order of arrival at each location, or by the time at which delivery capacity is projected to arrive at the geographic location.

Where the business process in this specification is used to determine the resources that will be consumed to execute the order, the resources may be at least one of human resources, computing resources, network resources, and money that will be consumed to execute the order. The resource may be paid out by the user who generated the order, by the delivery capacity that performed the order, or by the server, or by another device communicatively coupled to the server.

It can be seen that, the process in this specification can at least supplement data representing execution manners for pending orders, compare execution manners of orders in an area, and/or provide guidance for subsequent business processing of other orders with a priori knowledge about execution manners obtained from historical orders in the area.

The following describes the procedure of the service processing in this specification in detail.

As can be seen from the foregoing, the process in this specification depends on the trained model, and the determination process of each data required for training the model will be described below from three aspects of "determining a sample order", "determining a training sample", and "determining a label corresponding to the training sample".

Firstly, determining a sample order.

The training effect of the model directly influences the capability of the model. In order to effectively train the preset model, a sample order required by training needs to be determined before training.

In an optional embodiment of the present description, when determining the sample order, it may be determined, for each historical order, whether the historical order is a sample order or a pending order according to data generated when executing the historical order. Specifically, the process may be:

for each historical order, obtaining data generated when the historical order is executed historically, wherein the data comprises: at least one of the first data and the second data. Judging whether the data of the historical order comprises second data, if so, determining that the historical order is a sample order; if not, determining that the historical order is a pending order.

The second data in this specification may also be data acquired (may be acquired in a manner of collection) during execution of the sample order. The dimension of the second data representation execution mode in the specification is different from the dimension of the first data representation execution mode. Optionally, the characterization of the execution pattern by the second data is more accurate and/or interpretable than the first data. Optionally, the first data is more readily available than the second data.

However, the above description of the first data and the second data is only an exemplary explanation, and does not limit the first data and/or the second data.

Secondly, determining a training sample.

The process of generating data in this specification may be a process in which a terminal that executes the delivery capacity of an order automatically collects data, or a process in which data is generated according to the operation of the delivery capacity.

In an actual order execution scenario, there are usually a plurality of orders that are distributed and executed by capacity within one work cycle (e.g., one natural day). The data acquired may not be for the same order.

The training sample adopted in the process of training the preset model in the present specification may be the order as the minimum unit. The acquired data of each historical order should be processed to obtain data generated when the historical order is executed.

In addition, the training samples may also be the minimum unit of the task point, and a plurality of training samples and labels corresponding to the training samples may be obtained according to one sample order. The acquired data of each historical order should be processed to obtain the data generated at the task point when the historical order is executed.

Specifically, the process of processing the acquired data may be:

1) for each sample order, a task point for the sample order is determined.

Since the number of task points of each sample order may not be unique, for simplicity of description, only one of the task points of the sample order is taken as an example for the following description.

2) For the task point, a first specified range (which may be a geographical range) around the task point is determined according to a preset first distance. The preset first distance in this specification may be obtained from historical data and/or business objectives.

For example, a circle may be drawn for the task point with the task point as a center and the preset first distance as a radius, and a portion selected by the obtained circle may be used as a first designated range around the task point. The first designated range may be inside a preset area where the task point is located; the first designated range can also be at least partially overlapped with a preset area where the task point is located; the preset area where the task point is located may also be inside the first specified range.

In an alternative embodiment of the present disclosure, for a certain task point, the number of the preset distances used for determining the first specified range around the task point for the task point may be multiple, so that the first specified range of the task point is the preset area where the task point is located.

3) And for each time when the sample order is executed within the first specified range, determining first data corresponding to the time in the data of the sample order.

The first data corresponding to the time may be the first data generated at the time.

When the first data corresponding to the time is determined, the data not generated at the time may be removed, and the first data generated at the time may be retained.

4) And determining a training sample according to the first data corresponding to each moment and the time sequence of each first data.

Optionally, for a time, if the number of the first data generated at the time is multiple, the first data corresponding to the time may be represented in a data list. The resulting training sample may be a plurality of data lists arranged in a time sequence of individual time instants experienced within the first specified range.

In an alternative embodiment of the present description, the first data may be data of a wireless communication signal. Specifically, the wireless communication signal may be at least one of a network signal sent by a terminal (e.g., a terminal equipped for distribution capacity), a network signal (WIFI) in an environment searched by the terminal, and a call signal of the terminal.

In a practical scenario, the process of delivering the capacity fulfillment order needs to be assisted by the wireless communication capability of the terminal. Wireless communication signals associated with (received by and/or transmitted by) the terminal are readily available and have a degree of correlation with the manner in which the order is executed.

Specifically, according to the first data corresponding to each time and the time sequence of each first data, the process of determining the training sample may be:

according to the data of the wireless communication signals corresponding to the moment, at least one of the number of the wireless communication signals collected at the moment, the comprehensive signal strength of each wireless communication signal and the signal strength of each target wireless communication signal can be determined and used as the available data corresponding to the moment. Wherein the target wireless communication signal is: in a sequence formed by the collected signal intensity of each wireless communication signal from large to small, the signal intensity of the wireless communication signal is positioned before the preset sequence.

In an alternative embodiment of the present disclosure, the integrated signal strength of each wireless communication signal collected at the time may be used to characterize the modulus of each wireless communication signal collected at the time. Optionally, the integrated signal strength of each wireless communication signal collected at the time in this specification

Can be calculated by the following formula:

in the formula: n is the number of wireless communication signals collected at that moment; b is_iIs the signal strength of the ith wireless communication signal, i ≦ n.

Further, the preset order in this specification may be set according to a business objective. If the preset sequence is set to 20, the 20 wireless communication signals with the strongest signal strength in the n wireless communication signals are determined to be the target wireless communication signals. At this time, the feature corresponding to the time may include 22 dimensions at most, that is, the number of wireless communication signals (1 dimension), and the integrated signal strength

(1 dimension) and signal strength of the target wireless communication signal (20 dimensions).

In an actual scenario, 20 wireless communication signals may not be collected at a certain time, and when the number of collected wireless communication signals is smaller than the preset sequence value, the signal strength of the wireless communication signal with the phase difference between the number of collected wireless communication signals and the preset sequence value may be set to 0.

Secondly, determining the characteristics corresponding to the moment according to the available data corresponding to the moment.

Alternatively, the available data corresponding to the time may be directly used as the characteristic of the time.

And thirdly, determining a training sample according to the corresponding characteristics of each moment and the time sequence of each first data.

Optionally, the features corresponding to each time when the sample order is executed in the first specified range may be arranged according to the time sequence of each time to obtain the training sample.

And performing the operations of the previous steps for each sample order to obtain training samples required by the training model.

It can be seen that the training samples obtained through the processes in the present specification have a certain time sequence characteristic, that is, the training samples can reflect the change of the first data generated when the delivery capacity executes the historical order within the first specified range over time. When the model is trained according to the training sample with the time sequence characteristic, the model can learn the influence of different order execution modes on the change situation of the generated first data along with the time.

And thirdly, determining a label corresponding to the training sample.

In this specification, the label required for training the model is determined according to the execution mode of the sample order, and in order to determine the label of the sample order, the execution mode of the sample order should be determined first.

As can be seen from the foregoing, the execution manner of the sample order in the present specification may be known in various manners. The following description will be given taking an example in which the second data is used to determine the execution mode of the sample order.

The origin of the data of the historical orders is not particularly limited by the present specification. The data of the historical order may be at least part of data generated in the whole life cycle of the historical order and/or data obtained by processing at least part of data generated in the whole life cycle of the historical order.

In an actual scenario, each data serving as the first data and each data serving as the second data may be determined from the data of the historical orders according to at least one of a business rule, a data situation of the historical orders, a dividing standard of an execution mode, a type of the data of each historical order (the data type may be determined according to a data acquisition mode and/or a type of a functional module acquiring the data), and an amount of each type of data. Optionally, the first data may contain data of a different type and/or the first data may contain data of a different type. And determining the first data and determining the second data in a non-sequential order.

Taking the amount of each type of data and a preset business rule as an example, the first data and the second data are determined in each data. If the acceleration data and the speed data can represent the execution mode to a certain extent according to the preset business rule, and the amount of the acceleration data is relatively large in each data of the historical order, the speed data can be used as the first data, and the acceleration data can be used as the second data. At this time, the label determined by the second data is also more accurate, so that the model obtained by training according to the label also has better model capability.

In an alternative embodiment of the present disclosure, determining the label corresponding to the training sample may employ one or more of the following steps:

1) for the task point of the sample order, a second specified range (which may be a geographical range) around the task point is determined according to a preset second distance. The preset second distance in this specification may be obtained based on historical data and/or business objectives.

For example, a circle may be drawn for the task point with the task point as a center and the preset second distance as a radius, and a portion selected by the obtained circle may be used as a second specified range around the task point. The second designated area may be inside the preset area where the task point is located, the second designated area may at least partially overlap with the preset area where the task point is located, and the preset area where the task point is located may also be inside the second designated area.

In an alternative embodiment of the present specification, the preset area where the task point is located may be taken as a second designated range; the first specified range determined by the foregoing steps may also be taken as the second specified range.

2) And determining an execution mode adopted when the sample order is executed according to second data generated when the sample order is executed in the second specified range.

In an alternative embodiment of the present description, the second data may include barometric pressure data for the environment; the execution mode may include: at least one of an elevator execution mode and a walking execution mode is adopted. Then, through the model obtained by the process training in the specification, it can be determined whether the delivery capacity adopts the execution mode of going upstairs and downstairs of the elevator or the execution mode of going upstairs and downstairs of the walking when the pending order is executed at the task point.

Specifically, according to the second data generated when the sample order is executed within the second specified range, the process of determining the execution mode adopted when the sample order is executed may be:

determining a change in atmospheric pressure data of the environment while executing the sample order within a second specified range of the task point. The change may be a change over time, which may be characterized by a rate of change of the barometric pressure data over time.

Because the change of the air pressure along with the floor height is determined by natural factors, the floor height represented by the air pressure data of the environment has stronger accuracy and interpretability.

The time-dependent change of the air pressure data of the elevator up and down stairs is shown in fig. 2a, t₀At the moment the capacity is delivered into the elevator, t₁The moment the delivery capacity reaches the mission point, t₂The capacity is distributed away from the elevator at all times. The time-varying air pressure data of the execution mode of walking upstairs and downstairs is shown in FIG. 2b, T₀Constantly distributing capacity into stairs, T₁The moment of delivery capacity to the mission point, T₂The delivery capacity is moved away from the stairs at all times. It can be known that, because the walking speed is low, the change of the air pressure data collected by the execution mode of walking upstairs and downstairs is gentle (the change rate of the air pressure data along with the time is low); in contrast, the running speed of the elevator is high, and the change of the air pressure data acquired by the execution mode of ascending and descending of the elevator is steep (the change rate of the air pressure data along with time is high).

Therefore, the change situation of the air pressure data of the environment can better distinguish the execution mode of going upstairs and downstairs of the elevator from the execution mode of going upstairs and downstairs of the elevator.

In order to obtain the correlation between the change condition of the first data with time and the execution mode of the order, the model in this specification may be an LSTM (Long Short-Term Memory) neural network. In an alternative embodiment of the present description, the process of obtaining the execution of the order using the LSTM neural network may be as shown in fig. 3. And inputting the model into the output obtained by the characteristics at the j-1 th moment and the characteristics at the j-1 th moment to input the model, so as to obtain the output corresponding to the j moments of the model output.

The preset condition can be used for determining whether the delivery capacity is in an order execution mode of going upstairs by an elevator or in an order execution mode of going upstairs by walking.

The preset conditions may be derived from historical data and/or business objectives. For example, with the relationship between the change and a preset change rate threshold as a preset condition, the process of determining the execution manner may be: and determining a change rate threshold of the air pressure data according to the historical data. If the change rate of the second data determined by the sample order is larger than the change rate threshold value, determining that the change meets a preset condition, wherein the execution mode when the sample order is executed is the execution mode of an elevator; and if the change rate of the second data determined by the sample order is smaller than the change rate threshold value, determining that the change does not meet the preset condition, and executing the sample order in a walking execution mode.

In an alternative embodiment of the present disclosure, the preset condition may include a preset first condition and a preset second condition.

The preset first condition is used for judging whether the execution mode adopted by the delivery capacity execution order is the execution mode adopting an elevator. The second condition is preset for judging whether the execution mode adopted by the delivery capacity execution order is the mode executed by the user.

Specifically, if the change meets a preset first condition, determining that the execution mode when the sample order is executed is the execution mode of an elevator; if the change meets a preset second condition, determining that the execution mode when the sample order is executed is a mode executed by a user; if the first condition or the second condition is not satisfied, the execution mode when executing the sample order is determined to be the execution mode of walking. Optionally, the preset first condition corresponding variation degree is greater than the preset second condition corresponding variation degree.

The mode executed by the user can be that the delivery capacity does not go upstairs, and the user corresponding to the order is waited downstairs to take meals.

The preset first condition can be obtained according to historical data and/or a business target. For example, it may be determined whether a preset first condition is satisfied according to a relationship between the change and a preset first change rate threshold, and the process of determining the execution manner may be: a first rate of change threshold of the air pressure data is determined from the historical data. If the change rate of the air pressure data determined by a sample order is larger than the first change rate threshold value, determining that the change meets a preset first condition, wherein the execution mode when the sample order is executed is the execution mode of an elevator; and if the change rate of the air pressure data determined by the sample order is smaller than the first change rate threshold value, determining that the change does not meet the preset first condition, and executing the sample order in a manner other than that of an elevator.

The preset second condition may also be derived from historical data and/or business goals. For example, it may be determined whether a preset second condition is satisfied according to a relationship between the change and a preset second change rate threshold, and the process of determining the execution manner may be: a second rate of change threshold of the air pressure data is determined from the historical data. If the change rate of the air pressure data determined by the sample order is smaller than the second change rate threshold value, determining that the change meets a preset second condition, wherein the execution mode when the sample order is executed is a mode executed by a user; and if the change rate of the air pressure data determined by the sample order is greater than the second change rate threshold value, determining that the change does not meet a preset second condition, and executing the sample order in a mode which is not executed by the user.

Wherein the first rate of change threshold is greater than the second rate of change threshold.

If the change rate of the air pressure data determined by the sample order is smaller than the first change rate threshold value and larger than the second change rate threshold value, the change rate of the air pressure data determined by the sample order does not meet any one of a preset first condition and a preset second condition, and the execution mode when the sample order is executed is determined to be the execution side adopting walking.

And thirdly, determining the label of the sample order according to the execution mode of the sample order.

Alternatively, the execution mode of the sample order may be directly used as the label of the sample order. The label of the sample order may be one of an elevator-based execution, a walking-based execution, and a user-based execution.

And at this point, after the training samples required by the training model and the labels corresponding to the training samples are determined, the training samples and the labels determined in the above steps can be adopted to train the model, and the execution mode of the order to be determined is determined through the trained model.

As can be seen from the foregoing, in an alternative embodiment of the present disclosure, the first data may be data of a wireless communication signal, the second data may be barometric pressure data of the environment, and the execution mode may be an elevator up-and-down execution mode, or an elevator up-and-down execution mode. In an actual scenario, after the transportation capacity portable terminal enters the elevator, due to the shielding effect of the elevator on signals, data of wireless communication signals generated (received and/or transmitted) by the terminal is changed sharply compared with data generated outside the elevator. In addition, the change rule of the data of the wireless communication signal generated by the terminal is different from the change rule of the data of the wireless communication signal generated outside the elevator in the ascending and/or descending process of the elevator. So that the data of the wireless communication signal can characterize the execution mode to a certain extent.

In addition, the order may be executed by the user without going upstairs. If the rate of change of the data of the wireless communication signal generated during the order execution process is changed due to going upstairs and downstairs, the order execution mode is the mode executed by the user.

It can be seen that the training samples and labels obtained through the process in this specification enable at least the model to learn how to determine, based on changes in the data of the wireless communication signals, whether the execution mode of going up or down the elevator or the execution mode of going up or down the stairs is adopted in the process of executing the pending order.

And fourthly, planning a path when the unfinished order is executed.

After the execution mode is determined for each historical order, the execution mode of the historical order in a preset area can be determined according to the execution mode of each historical order, and the business corresponding to the order in the area is processed.

As previously mentioned, the business processes in this specification may be used to plan a path for the incomplete order to take when the delivery capacity executes the incomplete order. In an alternative embodiment of the present specification, the process of planning the path may be:

1) and determining each task point in each preset area in each task point of each historical order.

In some scenarios, a region may contain several task points.

2) And determining the execution mode corresponding to the area according to the execution mode of each historical order at each task point in the area.

At least one of the sample order and the pending order may be used as a historical order for use in determining how the order is to be executed in the area.

Optionally, the granularity of the regions partitioned by the present specification may be obtained according to the execution manner of the historical order. In the foregoing steps, the execution modes of the historical orders are obtained, and a certain geographic range may be initially divided according to a preset business rule to obtain a plurality of initial ranges. For each initial scope, the manner in which each order is executed within that initial scope is determined. And determining the similarity between the execution modes of the orders in the initial range as the similarity corresponding to the initial range. And judging whether the similarity corresponding to the initial range is greater than a preset similarity threshold, if so, indicating that the similarity of the historical orders in the execution in the initial range is high, and taking the initial range as an area. If not, the similarity of the historical orders in the initial range is low, multiple execution modes exist in the initial range, the initial range is further divided according to preset business rules to obtain a plurality of sub-initial ranges, each sub-initial range is re-determined as the initial range, and whether the similarity corresponding to the re-determined initial range is larger than a preset similarity threshold value or not is continuously judged. Until the initial range is determined to be the region.

Optionally, the execution manner of each task point in the area may be determined, and the execution manner with the largest occurrence frequency in each execution manner is used as the execution manner corresponding to the area.

3) And for each unfinished order, determining the area where the unfinished order is located in each area as a target area of the unfinished order.

The process of determining the target area for the incomplete order may be: the task point of the incomplete order is identified. The number of task points for the incomplete order may be multiple. For convenience of explanation, any task point of the incomplete order will be taken as an example for explanation. And determining the area where the task point is located in each preset area as a target area of the unfinished order.

4) And determining the execution mode of the unfinished order in the target area according to the execution mode corresponding to the target area.

The execution mode corresponding to the target area may be used as the execution mode of the unfinished order at the task point located in the area.

5) And planning a path for executing the unfinished order according to the execution mode of the unfinished order in the target area.

Optionally, when there are multiple target areas for the incomplete orders, a sub-path for executing the incomplete orders in the target area may be planned according to the execution manner of the incomplete orders in the target areas, and a path for executing the incomplete orders may be planned according to each path of the incomplete orders.

And fifthly, determining resources to be consumed for executing the unfinished order.

As previously mentioned, the business processes in this specification can also be used to determine the resources that will be consumed to execute the outstanding order. Then in an alternative embodiment of the present specification, the process of determining the resources to be consumed may also be:

1) for each incomplete order, determining an execution manner of the incomplete order in the area.

2) And determining the execution difficulty of the unfinished order according to the execution mode of the unfinished order in the area.

The "execution difficulty" in this specification may be used to characterize the severity of the expected execution of the incomplete order. The execution difficulty is related to the execution manner of the incomplete order in the area.

For example, if an incomplete order is executed in an area where the incomplete order is located by walking up or down a floor, the execution status of the incomplete order is more severe, and the execution of the incomplete order is more difficult.

3) And determining at least one of a path for executing the incomplete order, time required for executing the incomplete order, and resources to be consumed for executing the incomplete order according to the execution difficulty of the incomplete order in each area.

Optionally, the time required to execute the incomplete order is positively correlated with the execution difficulty of the incomplete order, and/or the resources consumed to execute the incomplete order is positively correlated with the execution difficulty of the incomplete order.

As can be seen from the foregoing, the incomplete orders in this specification may include orders to be sent. The process in this specification may predict that, under the condition that the order to be sent is sent by the user, the execution mode of the order to be sent in the area may be determined if there are multiple areas in which the order to be sent is located. And further determining the execution difficulty of the order to be sent according to the determined execution mode of the order to be sent.

Since the resource in this specification may be a resource (e.g., at least part of the delivery fee) borne by the user, the resource may be provided to the user, and if the user considers the resource to be too high, the user may refuse to send the order to be sent.

It can be seen that the process in this specification can influence the ordering behavior of the user by determining the execution mode of the order to be sent, and the influence can be to encourage the user to order or to inhibit the user from ordering. In the case of a large number of orders and insufficient delivery capacity, the process of the present specification can effectively adjust the "supply and demand balance" of the delivery capacity to the execution capacity of the orders. Optionally, the resource may also be provided to at least one of a delivery capacity, a merchant corresponding to the order, and a device (e.g., a terminal device communicatively connected to a server, etc.) that processes the order to be sent.

In addition, the processes described herein may also be used to determine the time required to execute the incomplete order. The time may be used to generate a commitment delivery time when the user generates an order to be sent, and/or when the user sends the order to be sent to the server.

Optionally, the user may be presented with at least one of the determined time required to execute the incomplete order, resources that will be consumed to execute the incomplete order, and a committed delivery time.

Sixthly, managing the transport capacity information of the distribution transport capacity.

As mentioned above, the business process in this specification can also be used to manage capacity information for delivering capacity.

In an alternative embodiment of the present description, the process may be: and aiming at the historical order, determining whether an execution mode of going upstairs is adopted in the process of delivering and executing the pending order according to the execution mode adopted when the pending order is executed, wherein the execution mode of going upstairs comprises at least one of an execution mode of adopting an elevator and an execution mode of adopting walking. And if so, managing the transport capacity information of the distribution transport capacity by adopting a preset first management mode. If not, managing the transport capacity information of the distribution transport capacity by adopting a preset second management mode.

In another alternative embodiment of the present specification, the process may further be: and determining the execution mode corresponding to the area according to the execution mode of each historical order executed in the area. And aiming at the historical order, determining the area where the historical order is located in each area as the target area of the historical order. And judging whether the execution mode of the historical order in the target area is matched with the execution mode corresponding to the target area. And if so, managing the transport capacity information of the distribution transport capacity by adopting a preset first management mode. If not, managing the transport capacity information of the distribution transport capacity by adopting a preset second management mode.

When the first management mode is adopted, the usability degree of the distribution capacity represented by the capacity information of the distribution capacity cannot be negatively influenced. The second management mode may negatively affect the availability of the delivery capacity as characterized by the capacity information of the delivery capacity.

Further, the process of managing the transportation capacity information of the distribution transportation capacity by using a preset first management mode may be: maintaining the availability of the dispensing capacity, or increasing the availability of the dispensing capacity.

The process of managing the transportation capacity information of the distribution transportation capacity by using the preset second management mode may be: reducing the availability of the delivery capacity.

The degree of availability in this specification is used to characterize: the distribution capacity itself affects the order execution effect (the execution effect can be characterized by the execution efficiency). The availability may be based on how the delivery capacity execution history order was executed. The availability may be characterized in terms of a rating, score, etc. of the delivery capacity.

Alternatively, the degree of availability is positively correlated to the performance effect. For example, the better a dispatch capacity has historically performed an order, the higher the dispatch capacity is available.

In the actual order execution process, the order execution effect of the delivery capacity is determined to a great extent by the order execution mode. If the user corresponding to the order is notified to take down the commodity corresponding to the order when the order is executed by the delivery capacity, the order execution efficiency is affected, the user experience is affected, and the order execution effect is difficult to guarantee, the execution of the order by the delivery capacity cannot meet the expected responsibility.

In another alternative embodiment of the present specification, the transportation capacity information for delivering the transportation capacity may be managed according to the operation of the user on the historical order, and the process may be: and aiming at the specified historical orders determined in the historical orders, determining the area where the specified historical orders are located as the target area of the specified historical orders. And judging whether the execution mode of the specified historical order is matched with the execution mode corresponding to the target area. If so, managing the transportation capacity information of the delivery transportation capacity by adopting a preset first management mode (for example, judging that the execution effect of the delivery transportation capacity on the order is not up to the expected responsibility). If not, the transportation capacity information of the delivery transportation capacity is managed by adopting a preset second management mode (for example, the execution effect of the delivery transportation capacity on the order is judged not to reach the expected responsibility).

The process of determining the designated historical order may be to receive designated data sent by the user, where the designated data is used to indicate the execution effect of the order, and optionally, the designated data may be the evaluation of the user for the designated historical order. And if the execution effect of the historical order corresponding to the specified data is determined to not reach the preset standard execution effect according to the specified data, determining the historical order corresponding to the specified data as the specified historical order.

Wherein the execution effect can be characterized by execution efficiency. The effect of the execution that the preset standard is not reached may be: the execution efficiency is lower than the preset standard execution efficiency, for example, the actual delivery time is later than the committed delivery time.

In addition, the execution mode of the specified historical order can be obtained according to the second data of the specified historical order. If the designated historical order has no second data or the second data of the designated historical order is unavailable, the execution mode of the designated historical order can be determined according to the first data of the designated historical order by adopting the trained model.

Based on the same idea, the embodiments of the present specification further provide a service processing apparatus corresponding to the process shown in fig. 1, and the service processing apparatus is shown in fig. 4.

Fig. 4 is a schematic structural diagram of a service processing apparatus provided in an embodiment of this specification, where the service processing apparatus may include one or more of the following modules:

an order determination module 400 configured to determine, among the historical orders, a sample order whose execution manner is known and a pending order whose execution manner is unknown;

a training sample and label determination module 402 configured to determine, for each sample order, a training sample according to the acquired first data of the sample order; determining a label according to the execution mode of the sample order;

a training module 404 configured to train a preset model according to the determined training samples and labels to obtain a trained model;

an execution mode determining module 406, configured to determine, for each pending order, an execution mode to be used when the pending order is executed, according to the first data of the pending order, by using the trained model;

a historical order determination module 408 configured to determine, for each preset area, a historical order executed in the area among the historical orders;

a service processing module 410, configured to process a service corresponding to each historical order executed in the area according to an execution manner of each historical order executed in the area, where the order in the area includes: at least one of historical orders in the area, incomplete orders in the area.

It can be seen that the apparatus in this specification can at least supplement missing data representing execution modes for the order to be ordered, and after obtaining the execution modes of each historical order, can process the service corresponding to each order in the area according to the execution modes of the historical orders in the area by taking the area as a unit. It can be seen that the processes in this specification can at least compare the execution patterns of orders in an area, and/or can use the execution pattern of historical orders in the area as a priori of other orders in the area, so that each order can be properly processed.

Optionally, the order determination module 400 may include a data determination sub-module and a determination sub-module.

A data determination sub-module configured to, for each historical order, obtain data generated when the historical order was historically executed, the data comprising: at least one of the first data and the second data.

And the judging submodule is configured to judge whether the data of the historical order includes second data, determine that the historical order is a sample order if the data of the historical order includes the second data, and determine that the historical order is an undetermined order if the data of the historical order does not include the second data.

Optionally, the training sample and label determination module 402 may include a training sample determination sub-module.

And the training sample determining submodule is configured to determine a first specified range around the task point according to a preset first distance aiming at the task point of the sample order. And for each time when the sample order is executed within the first specified range, determining first data corresponding to the time in the data of the sample order. And determining a training sample according to the first data corresponding to each moment and the time sequence of each first data.

Optionally, the training sample determining submodule is further configured to determine, according to the data of the wireless communication signal corresponding to the time, at least one of the number of the wireless communication signals acquired at the time, the integrated signal strength of each wireless communication signal, and the signal strength of each target wireless communication signal as available data corresponding to the time; wherein the target wireless communication signal is: in a sequence formed by the collected signal intensity of each wireless communication signal from large to small, the signal intensity of the wireless communication signal is positioned before the preset sequence. And determining the characteristics corresponding to the moment according to the available data corresponding to the moment. And determining a training sample according to the corresponding characteristics of each moment and the time sequence of each first data.

Optionally, the training sample and label determination module 402 may include a label determination sub-module.

And the label determining submodule is configured to determine a second specified range around the task point according to the preset second distance aiming at the task point of the sample order. And determining an execution mode adopted when the sample order is executed according to second data generated when the sample order is executed in the second specified range. And determining the label of the sample order according to the execution mode of the sample order.

Optionally, the tag determination sub-module is further configured for determining a change in atmospheric pressure data of the environment when the sample order is executed within a second specified range of the task point. If the change meets a preset first condition, determining that the execution mode when the sample order is executed is the execution mode of an elevator; and if not, determining that the execution mode when executing the sample order is the execution mode of walking.

Optionally, the business processing module 410 may include a designated execution mode determination sub-module, an area determination sub-module, an execution mode first determination sub-module, and a business processing sub-module.

And the specified execution mode determining submodule is configured to determine the execution mode corresponding to the area according to the execution mode of each historical order executed in the area.

And the area determining submodule is configured to determine, for each order, an area where the order is located in each area as a target area of the order.

And the execution mode first determining submodule is configured to process the service corresponding to the order according to the execution mode corresponding to the target area.

Optionally, the business processing module 410 may further include an execution mode second determining sub-module, an execution difficulty determining sub-module, and an information determining sub-module.

And the execution mode second determination submodule is configured to determine an execution mode of the unfinished order in the area.

And the execution difficulty determining sub-module is configured to determine the execution difficulty of the unfinished order according to the execution mode of the unfinished order in the area.

And the information determining submodule is configured to determine at least one of a path for executing the incomplete order, time required for executing the incomplete order, resources to be consumed for executing the incomplete order, and information displayed to a user corresponding to the incomplete order according to the execution difficulty of the incomplete order in each area.

Embodiments of the present specification also provide a computer-readable storage medium, where the storage medium stores a computer program, and the computer program can be used to execute any of the above business processing procedures.

The embodiment of the present specification also provides a schematic structural diagram of the electronic device shown in fig. 5. As shown in fig. 5, at the hardware level, the electronic device may include a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include hardware required for other services. The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to realize any one of the above-mentioned business processing processes.

Of course, besides the software implementation, the present specification does not exclude other implementations, such as a combination of logic devices or software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or a logic device.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.

Claims

1. A method for processing a service, the method comprising:

2. The method of claim 1, wherein determining, among the historical orders, a sample order for which execution is known and a pending order for which execution is unknown comprises:

3. The method of claim 1, wherein determining a training sample based on the obtained first data of the sample order comprises:

4. The method of claim 3, wherein the first data comprises: data of a wireless communication signal;

5. The method of claim 2, wherein determining the label according to the execution mode of the sample order specifically comprises:

6. The method of claim 5, wherein the second data comprises: atmospheric pressure data of the environment; the execution mode comprises the following steps: at least one of an elevator execution mode and a walking execution mode;

7. The method according to any one of claims 1 to 6, wherein processing the service corresponding to the order in the area according to the execution mode of each historical order executed in the area specifically includes:

8. A traffic processing apparatus, characterized in that the apparatus comprises:

9. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1-7.

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1-7 when executing the program.